Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Spatial Reasoning on VSP
Loading...
85.83
Accuracy
Visual-OPSD
-3.4332
19.7409
42.915
66.0891
Jun 17, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Visual-OPSD
3-run average=true, La...
2026.06
85.83
ThinkMorph
3-run average=true, La...
2026.06
75.83
GPT-5
3-run average=true
2026.06
57.33
Visual-OPSD-Noise
3-run average=true, La...
2026.06
50.83
Text-only SFT
3-run average=true, La...
2026.06
49.17
Qwen3-VL-32B
3-run average=true
2026.06
43.5
GPT-4o
3-run average=true
2026.06
33.5
Qwen3-VL-8B
3-run average=true
2026.06
22
InternVL3.5-38B
3-run average=true
2026.06
20.16
InternVL3.5-8B
3-run average=true
2026.06
8.17
Chameleon-7B
3-run average=true
2026.06
0.83
BAGEL-7B
3-run average=true
2026.06
0.83
Janus-Pro-7B
3-run average=true
2026.06
0
Feedback
Search any
task
Search any
task